Problem Statement¶

Context¶

AllLife Bank is a US bank that has a growing customer base. The majority of these customers are liability customers (depositors) with varying sizes of deposits. The number of customers who are also borrowers (asset customers) is quite small, and the bank is interested in expanding this base rapidly to bring in more loan business and in the process, earn more through the interest on loans. In particular, the management wants to explore ways of converting its liability customers to personal loan customers (while retaining them as depositors).

A campaign that the bank ran last year for liability customers showed a healthy conversion rate of over 9% success. This has encouraged the retail marketing department to devise campaigns with better target marketing to increase the success ratio.

You as a Data scientist at AllLife bank have to build a model that will help the marketing department to identify the potential customers who have a higher probability of purchasing the loan.

Objective¶

To predict whether a liability customer will buy personal loans, to understand which customer attributes are most significant in driving purchases, and identify which segment of customers to target more.

Data Dictionary¶

  • ID: Customer ID
  • Age: Customer’s age in completed years
  • Experience: #years of professional experience
  • Income: Annual income of the customer (in thousand dollars)
  • ZIP Code: Home Address ZIP code.
  • Family: the Family size of the customer
  • CCAvg: Average spending on credit cards per month (in thousand dollars)
  • Education: Education Level. 1: Undergrad; 2: Graduate;3: Advanced/Professional
  • Mortgage: Value of house mortgage if any. (in thousand dollars)
  • Personal_Loan: Did this customer accept the personal loan offered in the last campaign? (0: No, 1: Yes)
  • Securities_Account: Does the customer have securities account with the bank? (0: No, 1: Yes)
  • CD_Account: Does the customer have a certificate of deposit (CD) account with the bank? (0: No, 1: Yes)
  • Online: Do customers use internet banking facilities? (0: No, 1: Yes)
  • CreditCard: Does the customer use a credit card issued by any other Bank (excluding All life Bank)? (0: No, 1: Yes)

Importing necessary libraries¶

In [6]:
# Installing the libraries with the specified version.
!pip install numpy==1.25.2 pandas==1.5.3 matplotlib==3.7.1 seaborn==0.13.1 scikit-learn==1.2.2 sklearn-pandas==2.2.0 -q --user

Note:

  1. After running the above cell, kindly restart the notebook kernel (for Jupyter Notebook) or runtime (for Google Colab), write the relevant code for the project from the next cell, and run all cells sequentially from the next cell.

  2. On executing the above line of code, you might see a warning regarding package dependencies. This error message can be ignored as the above code ensures that all necessary libraries and their dependencies are maintained to successfully execute the code in this notebook.

In [8]:
# Libraries to help with reading and manipulating data
import pandas as pd
import numpy as np

# libaries to help with data visualization
import matplotlib.pyplot as plt
import seaborn as sns

# Library to split data
from sklearn.model_selection import train_test_split

# To build model for prediction
from sklearn.tree import DecisionTreeClassifier
from sklearn import tree

# To get diferent metric scores
from sklearn.metrics import (
    f1_score,
    accuracy_score,
    recall_score,
    precision_score,
    confusion_matrix,
)

# to suppress unnecessary warnings
import warnings
warnings.filterwarnings("ignore")

Loading the dataset¶

In [10]:
Loan = pd.read_csv("Loan_Modelling.csv")   ##  Read the data
In [11]:
# copying data to another variable to avoid any changes to original data
data = Loan.copy()

Data Overview¶

In [13]:
data.head() # View the first 5 rows of the dataset.
Out[13]:
ID Age Experience Income ZIPCode Family CCAvg Education Mortgage Personal_Loan Securities_Account CD_Account Online CreditCard
0 1 25 1 49 91107 4 1.6 1 0 0 1 0 0 0
1 2 45 19 34 90089 3 1.5 1 0 0 1 0 0 0
2 3 39 15 11 94720 1 1.0 1 0 0 0 0 0 0
3 4 35 9 100 94112 1 2.7 2 0 0 0 0 0 0
4 5 35 8 45 91330 4 1.0 2 0 0 0 0 0 1
In [14]:
data.tail()  # View the last 5 rows of the dataset.
Out[14]:
ID Age Experience Income ZIPCode Family CCAvg Education Mortgage Personal_Loan Securities_Account CD_Account Online CreditCard
4995 4996 29 3 40 92697 1 1.9 3 0 0 0 0 1 0
4996 4997 30 4 15 92037 4 0.4 1 85 0 0 0 1 0
4997 4998 63 39 24 93023 2 0.3 3 0 0 0 0 0 0
4998 4999 65 40 49 90034 3 0.5 2 0 0 0 0 1 0
4999 5000 28 4 83 92612 3 0.8 1 0 0 0 0 1 1
In [15]:
data.shape  # To get the shape of the data
Out[15]:
(5000, 14)
In [16]:
data.size   # To get size of the data
Out[16]:
70000
In [17]:
data.info()  # To check the dataTypes  

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 5000 entries, 0 to 4999
Data columns (total 14 columns):
 #   Column              Non-Null Count  Dtype  
---  ------              --------------  -----  
 0   ID                  5000 non-null   int64  
 1   Age                 5000 non-null   int64  
 2   Experience          5000 non-null   int64  
 3   Income              5000 non-null   int64  
 4   ZIPCode             5000 non-null   int64  
 5   Family              5000 non-null   int64  
 6   CCAvg               5000 non-null   float64
 7   Education           5000 non-null   int64  
 8   Mortgage            5000 non-null   int64  
 9   Personal_Loan       5000 non-null   int64  
 10  Securities_Account  5000 non-null   int64  
 11  CD_Account          5000 non-null   int64  
 12  Online              5000 non-null   int64  
 13  CreditCard          5000 non-null   int64  
dtypes: float64(1), int64(13)
memory usage: 547.0 KB
In [18]:
data.describe().T  # To get the statistical summary of the data
Out[18]:
count mean std min 25% 50% 75% max
ID 5000.0 2500.500000 1443.520003 1.0 1250.75 2500.5 3750.25 5000.0
Age 5000.0 45.338400 11.463166 23.0 35.00 45.0 55.00 67.0
Experience 5000.0 20.104600 11.467954 -3.0 10.00 20.0 30.00 43.0
Income 5000.0 73.774200 46.033729 8.0 39.00 64.0 98.00 224.0
ZIPCode 5000.0 93169.257000 1759.455086 90005.0 91911.00 93437.0 94608.00 96651.0
Family 5000.0 2.396400 1.147663 1.0 1.00 2.0 3.00 4.0
CCAvg 5000.0 1.937938 1.747659 0.0 0.70 1.5 2.50 10.0
Education 5000.0 1.881000 0.839869 1.0 1.00 2.0 3.00 3.0
Mortgage 5000.0 56.498800 101.713802 0.0 0.00 0.0 101.00 635.0
Personal_Loan 5000.0 0.096000 0.294621 0.0 0.00 0.0 0.00 1.0
Securities_Account 5000.0 0.104400 0.305809 0.0 0.00 0.0 0.00 1.0
CD_Account 5000.0 0.060400 0.238250 0.0 0.00 0.0 0.00 1.0
Online 5000.0 0.596800 0.490589 0.0 0.00 1.0 1.00 1.0
CreditCard 5000.0 0.294000 0.455637 0.0 0.00 0.0 1.00 1.0
In [19]:
data.duplicated().sum()
Out[19]:
0
In [20]:
data.nunique()
Out[20]:
ID                    5000
Age                     45
Experience              47
Income                 162
ZIPCode                467
Family                   4
CCAvg                  108
Education                3
Mortgage               347
Personal_Loan            2
Securities_Account       2
CD_Account               2
Online                   2
CreditCard               2
dtype: int64
Observations¶
The dataset contains 5,000 rows and 14 columns, representing customer demographics and financial behavior.

No missing data or duplicate entries were found, which simplifies preprocessing.

Most variables are numerical or binary, and do not require extensive encoding (except Education and ZIPCode).

The target variable Personal_Loan is binary, suitable for classification models.

ZIPCode has many unique values (high cardinality), which may not be useful without grouping or dropping.

Experience is nearly identical to Age - X (perfectly correlated) — consider dropping it to avoid multicollinearity.

Exploratory Data Analysis.¶

  • EDA is an important part of any project involving data.
  • It is important to investigate and understand the data better before building a model with it.
  • A few questions have been mentioned below which will help you approach the analysis in the right manner and generate insights from the data.
  • A thorough analysis of the data, in addition to the questions mentioned below, should be done.

Data Preprocessing¶

  • Missing value treatment
  • Feature engineering (if needed)
  • Outlier detection and treatment (if needed)
  • Preparing data for modeling
  • Any other preprocessing steps (if needed)
In [26]:
data = data.drop('ID', axis=1)  # The code to drop a column from the dataframe

Checking for Anomalous Values¶

In [28]:
data["Experience"].unique()
Out[28]:
array([ 1, 19, 15,  9,  8, 13, 27, 24, 10, 39,  5, 23, 32, 41, 30, 14, 18,
       21, 28, 31, 11, 16, 20, 35,  6, 25,  7, 12, 26, 37, 17,  2, 36, 29,
        3, 22, -1, 34,  0, 38, 40, 33,  4, -2, 42, -3, 43])
In [29]:
# checking for experience <0
data[data["Experience"] < 0]["Experience"].unique()
Out[29]:
array([-1, -2, -3])
In [30]:
# Correcting the experience values
data["Experience"].replace(-1, 1, inplace=True)
data["Experience"].replace(-2, 2, inplace=True)
data["Experience"].replace(-3, 3, inplace=True)
In [31]:
data["Education"].unique()
Out[31]:
array([1, 2, 3])

Feature Engineering¶

In [33]:
# checking the number of uniques in the zip code
data["ZIPCode"].nunique()
Out[33]:
467
In [34]:
data["ZIPCode"] = data["ZIPCode"].astype(str)
print(
    "Number of unique values if we take first two digits of ZIPCode: ",
    data["ZIPCode"].str[0:2].nunique(),
)
data["ZIPCode"] = data["ZIPCode"].str[0:2]

data["ZIPCode"] = data["ZIPCode"].astype("category")

Number of unique values if we take first two digits of ZIPCode:  7
In [35]:
# Converting the data type of categorical features to 'category'
cat_cols = [
    "Education",
    "Personal_Loan",
    "Securities_Account",
    "CD_Account",
    "Online",
    "CreditCard",
    "ZIPCode",
]
data[cat_cols] = data[cat_cols].astype("category")

Univariate Analysis¶

In [37]:
def histogram_boxplot(data, feature, figsize=(12, 7), kde=False, bins=None):
    """
    Boxplot and histogram combined

    data: dataframe
    feature: dataframe column
    figsize: size of figure (default (12,7))
    kde: whether to show the density curve (default False)
    bins: number of bins for histogram (default None)
    """
    f2, (ax_box2, ax_hist2) = plt.subplots(
        nrows=2,  # Number of rows of the subplot grid= 2
        sharex=True,  # x-axis will be shared among all subplots
        gridspec_kw={"height_ratios": (0.25, 0.75)},
        figsize=figsize,
    )  # creating the 2 subplots
    sns.boxplot(
        data=data, x=feature, ax=ax_box2, showmeans=True, color="violet"
    )  # boxplot will be created and a star will indicate the mean value of the column
    sns.histplot(
        data=data, x=feature, kde=kde, ax=ax_hist2, bins=bins, palette="winter"
    ) if bins else sns.histplot(
        data=data, x=feature, kde=kde, ax=ax_hist2
    )  # For histogram
    ax_hist2.axvline(
        data[feature].mean(), color="green", linestyle="--"
    )  # Add mean to the histogram
    ax_hist2.axvline(
        data[feature].median(), color="black", linestyle="-"
    )  # Add median to the histogram
In [38]:
# function to create labeled barplots


def labeled_barplot(data, feature, perc=False, n=None):
    """
    Barplot with percentage at the top

    data: dataframe
    feature: dataframe column
    perc: whether to display percentages instead of count (default is False)
    n: displays the top n category levels (default is None, i.e., display all levels)
    """

    total = len(data[feature])  # length of the column
    count = data[feature].nunique()
    if n is None:
        plt.figure(figsize=(count + 1, 5))
    else:
        plt.figure(figsize=(n + 1, 5))

    plt.xticks(rotation=90, fontsize=15)
    ax = sns.countplot(
        data=data,
        x=feature,
        palette="Paired",
        order=data[feature].value_counts().index[:n].sort_values(),
    )

    for p in ax.patches:
        if perc == True:
            label = "{:.1f}%".format(
                100 * p.get_height() / total
            )  # percentage of each class of the category
        else:
            label = p.get_height()  # count of each level of the category

        x = p.get_x() + p.get_width() / 2  # width of the plot
        y = p.get_height()  # height of the plot

        ax.annotate(
            label,
            (x, y),
            ha="center",
            va="center",
            size=12,
            xytext=(0, 5),
            textcoords="offset points",
        )  # annotate the percentage

    plt.show()  # show the plot

Observations on Age¶

In [40]:
histogram_boxplot(data, "Age")
No description has been provided for this image

Observations on Experience¶

In [42]:
histogram_boxplot(data, "Experience") # The code to create histogram_boxplot for experience
No description has been provided for this image

Observations on Income¶

In [44]:
histogram_boxplot(data, "Income")  # The code to create histogram_boxplot for Income
No description has been provided for this image

Observations on CCAvg¶

In [46]:
histogram_boxplot(data, "CCAvg")  # The code to create histogram_boxplot for CCAvg
No description has been provided for this image

Observations on Mortgage¶

In [48]:
histogram_boxplot(data, "Mortgage")  # The code to create histogram_boxplot for Mortgage
No description has been provided for this image

Observations on Family¶

In [50]:
labeled_barplot(data, "Family", perc=True)
No description has been provided for this image

Observations on Education¶

In [52]:
labeled_barplot(data, "Education", perc=True)   # The code to create labeled_barplot for Education
No description has been provided for this image

Observations on Securities_Account¶

In [54]:
labeled_barplot(data, "Securities_Account", perc=True )   # The code to create labeled_barplot for Securities_Account
No description has been provided for this image

Observations on CD_Account¶

In [56]:
labeled_barplot(data, "CD_Account", perc=True)   # The code to create labeled_barplot for CD_Account
No description has been provided for this image

Observations on Online¶

In [58]:
labeled_barplot(data, "Online", perc=True)   # The code to create labeled_barplot for Online
No description has been provided for this image

Observation on ZIPCode¶

In [60]:
labeled_barplot(data, "ZIPCode", perc=True)   # The code to create labeled_barplot for ZIPCode
No description has been provided for this image

Observation on CreditCard¶

In [62]:
labeled_barplot(data, "CreditCard", perc=True)   # The code to create labeled_barplot for CreditCard
No description has been provided for this image
Observations — Univariate Analysis¶
Most numerical variables such as Income, CCAvg, and Mortgage show right-skewed distributions, indicating that most customers have low values with a few having very high values.

Categorical variables like Family, Education, CreditCard, and CD_Account exhibit imbalanced distributions — for example, most customers belong to smaller families or have no credit card.

The target variable Personal_Loan is skewed toward 0 (non-loan customers), highlighting a class imbalance problem.

Bivariate Analysis¶

In [65]:
def stacked_barplot(data, predictor, target):
    """
    Print the category counts and plot a stacked bar chart

    data: dataframe
    predictor: independent variable
    target: target variable
    """
    count = data[predictor].nunique()
    sorter = data[target].value_counts().index[-1]
    tab1 = pd.crosstab(data[predictor], data[target], margins=True).sort_values(
        by=sorter, ascending=False
    )
    print(tab1)
    print("-" * 120)
    tab = pd.crosstab(data[predictor], data[target], normalize="index").sort_values(
        by=sorter, ascending=False
    )
    tab.plot(kind="bar", stacked=True, figsize=(count + 5, 5))
    plt.legend(
        loc="lower left", frameon=False,
    )
    plt.legend(loc="upper left", bbox_to_anchor=(1, 1))
    plt.show()
In [66]:
### function to plot distributions wrt target


def distribution_plot_wrt_target(data, predictor, target):

    fig, axs = plt.subplots(2, 2, figsize=(12, 10))

    target_uniq = data[target].unique()

    axs[0, 0].set_title("Distribution of target for target=" + str(target_uniq[0]))
    sns.histplot(
        data=data[data[target] == target_uniq[0]],
        x=predictor,
        kde=True,
        ax=axs[0, 0],
        color="teal",
        stat="density",
    )

    axs[0, 1].set_title("Distribution of target for target=" + str(target_uniq[1]))
    sns.histplot(
        data=data[data[target] == target_uniq[1]],
        x=predictor,
        kde=True,
        ax=axs[0, 1],
        color="orange",
        stat="density",
    )

    axs[1, 0].set_title("Boxplot w.r.t target")
    sns.boxplot(data=data, x=target, y=predictor, ax=axs[1, 0], palette="gist_rainbow")

    axs[1, 1].set_title("Boxplot (without outliers) w.r.t target")
    sns.boxplot(
        data=data,
        x=target,
        y=predictor,
        ax=axs[1, 1],
        showfliers=False,
        palette="gist_rainbow",
    )

    plt.tight_layout()
    plt.show()### function to plot distributions wrt target


def distribution_plot_wrt_target(data, predictor, target):

    fig, axs = plt.subplots(2, 2, figsize=(12, 10))

    target_uniq = data[target].unique()

    axs[0, 0].set_title("Distribution of target for target=" + str(target_uniq[0]))
    sns.histplot(
        data=data[data[target] == target_uniq[0]],
        x=predictor,
        kde=True,
        ax=axs[0, 0],
        color="teal",
        stat="density",
    )

    axs[0, 1].set_title("Distribution of target for target=" + str(target_uniq[1]))
    sns.histplot(
        data=data[data[target] == target_uniq[1]],
        x=predictor,
        kde=True,
        ax=axs[0, 1],
        color="orange",
        stat="density",
    )

    axs[1, 0].set_title("Boxplot w.r.t target")
    sns.boxplot(data=data, x=target, y=predictor, ax=axs[1, 0], palette="gist_rainbow")

    axs[1, 1].set_title("Boxplot (without outliers) w.r.t target")
    sns.boxplot(
        data=data,
        x=target,
        y=predictor,
        ax=axs[1, 1],
        showfliers=False,
        palette="gist_rainbow",
    )

    plt.tight_layout()
    plt.show()

Correlation check¶

In [68]:
plt.figure(figsize=(15, 7))
sns.heatmap(data.corr(numeric_only=True), annot=True, vmin=-1, vmax=1, fmt=".2f", cmap="Spectral") # The code to get the heatmap of the data
plt.show()
No description has been provided for this image

Let's check how a customer's interest in purchasing a loan varies with their education¶

In [70]:
stacked_barplot(data, "Education", "Personal_Loan")

Personal_Loan     0    1   All
Education                     
All            4520  480  5000
3              1296  205  1501
2              1221  182  1403
1              2003   93  2096
------------------------------------------------------------------------------------------------------------------------
No description has been provided for this image

Personal_Loan vs Family¶

In [72]:
stacked_barplot(data,"Family", "Personal_Loan")  ## The code to plot stacked barplot for Personal Loan and Family

Personal_Loan     0    1   All
Family                        
All            4520  480  5000
4              1088  134  1222
3               877  133  1010
1              1365  107  1472
2              1190  106  1296
------------------------------------------------------------------------------------------------------------------------
No description has been provided for this image

Personal_Loan vs Securities_Account¶

In [74]:
stacked_barplot(data,"Securities_Account", "Personal_Loan") # The code to plot stacked barplot for Personal Loan and Securities_Account

Personal_Loan          0    1   All
Securities_Account                 
All                 4520  480  5000
0                   4058  420  4478
1                    462   60   522
------------------------------------------------------------------------------------------------------------------------
No description has been provided for this image

Personal_Loan vs CD_Account¶

In [76]:
stacked_barplot(data,"CD_Account", "Personal_Loan") # The code to plot stacked barplot for Personal Loan and CD_Account

Personal_Loan     0    1   All
CD_Account                    
All            4520  480  5000
0              4358  340  4698
1               162  140   302
------------------------------------------------------------------------------------------------------------------------
No description has been provided for this image

Personal_Loan vs Online¶

In [78]:
stacked_barplot(data,"Online", "Personal_Loan") # The code to plot stacked barplot for Personal Loan and Online

Personal_Loan     0    1   All
Online                        
All            4520  480  5000
1              2693  291  2984
0              1827  189  2016
------------------------------------------------------------------------------------------------------------------------
No description has been provided for this image

Personal_Loan vs CreditCard¶

In [80]:
stacked_barplot(data,"CreditCard", "Personal_Loan") # The code to plot stacked barplot for Personal Loan and CreditCard

Personal_Loan     0    1   All
CreditCard                    
All            4520  480  5000
0              3193  337  3530
1              1327  143  1470
------------------------------------------------------------------------------------------------------------------------
No description has been provided for this image

Personal_Loan vs ZIPCode¶

In [82]:
stacked_barplot(data,"ZIPCode", "Personal_Loan") # The code to plot stacked barplot for Personal Loan and ZIPCode

Personal_Loan     0    1   All
ZIPCode                       
All            4520  480  5000
94             1334  138  1472
92              894   94   988
95              735   80   815
90              636   67   703
91              510   55   565
93              374   43   417
96               37    3    40
------------------------------------------------------------------------------------------------------------------------
No description has been provided for this image

Let's check how a customer's interest in purchasing a loan varies with their age¶

In [84]:
distribution_plot_wrt_target(data, "Age", "Personal_Loan")
No description has been provided for this image

Personal Loan vs Experience¶

In [86]:
distribution_plot_wrt_target(data, "Experience", "Personal_Loan") # The code to plot stacked barplot for Personal Loan and Experience
No description has been provided for this image

Personal Loan vs Income¶

In [88]:
distribution_plot_wrt_target(data, "Income", "Personal_Loan") # The code to plot stacked barplot for Personal Loan and Income
No description has been provided for this image

Personal Loan vs CCAvg¶

In [90]:
distribution_plot_wrt_target(data, "CCAvg", "Personal_Loan") # The code to plot stacked barplot for Personal Loan and CCAvg
No description has been provided for this image

Outlier Detection¶

In [92]:
Q1 = data.select_dtypes(include=["float64", "int64"]).quantile(0.25)  # To find the 25th percentile and 75th percentile.
Q3 = data.select_dtypes(include=["float64", "int64"]).quantile(0.75)

IQR = Q3 - Q1  # Inter Quantile Range (75th perentile - 25th percentile)

lower = (
    Q1 - 1.5 * IQR
)  # Finding lower and upper bounds for all values. All values outside these bounds are outliers
upper = Q3 + 1.5 * IQR
In [93]:
(
    (data.select_dtypes(include=["float64", "int64"]) < lower)
    | (data.select_dtypes(include=["float64", "int64"]) > upper)
).sum() / len(data) * 100
Out[93]:
Age           0.00
Experience    0.00
Income        1.92
Family        0.00
CCAvg         6.48
Mortgage      5.82
dtype: float64

Plot a simple pair plot to view if there is correlation between the data set variables¶

In [95]:
plt.figure(figsize=(15,15))
# sns.pairplot(loan, diag_kind='kde')
sns.pairplot(data, hue="Personal_Loan")
plt.show()

<Figure size 1500x1500 with 0 Axes>
No description has been provided for this image
Observations for Bivariate Analysis¶
Income and CCAvg: Customers with higher income and higher average credit card spending are more likely to take personal loans.

Education: Loan acceptance increases with education level, especially among those with graduate or advanced degrees.

Age: Loan uptake is higher in the 30–40 age group, and decreases for older and very young customers.

CD_Account and Securities_Account: Customers with existing CD accounts are significantly more likely to accept a loan.
Observations — Outlier Detection¶
Outliers were detected in numeric variables like Income, CCAvg, and Mortgage, especially on the higher end.

These outliers may impact model performance by skewing the decision boundaries, especially in algorithms sensitive to scale like logistic regression or k-NN.

Depending on the modeling technique, consider capping, log-transforming, or removing extreme outliers for robustness.
Observations for EDA¶
The distribution of key numeric features such as Income, CCAvg, and Mortgage is right-skewed, indicating a concentration of customers at lower values with a few high-value outliers.

A large proportion of customers do not own a mortgage or a credit card, which may influence their loan approval likelihood.

The Personal_Loan target variable is imbalanced, with relatively fewer customers opting for a personal loan.

Features like Income, CCAvg, and CD_Account exhibit a strong relationship with loan purchase decisions.

Higher education levels and middle-aged customers (30–40 years) tend to show greater interest in personal loans, revealing potential customer segments.

Questions: What is the distribution of mortgage attribute? Are there any noticeable patterns or outliers in the distribution?

Observation: Most customers have a Mortgage of 0, indicating many don't have existing mortgages. However, there are some outliers with very high mortgage values, which could skew model performance if not handled properly.

Questions: 2. How many customers have credit cards?

Observation: A significant portion of customers do not have credit cards. The ratio is important when considering cross-sell opportunities or risk profiling.

Questions: What are the attributes that have a strong correlation with the target attribute (personal loan)?

Observation: Attributes like Income, CCAvg, CD_Account, and Education show a positive correlation with Personal_Loan. These are key candidates for model features.

Questions: How does a customer's interest in purchasing a loan vary with their age?

Observation: Loan interest peaks around ages 30–40. Younger and much older customers are less likely to opt for personal loans.

Questions: How does a customer's interest in purchasing a loan vary with their education?

Observation: Customers with higher education levels (2 and 3) are more likely to purchase loans, possibly due to better income profiles or financial literacy.

Data Preparation for Modeling¶

In [105]:
# dropping Experience as it is perfectly correlated with Age
X = data.drop(["Personal_Loan", "Experience"], axis=1)
Y = data["Personal_Loan"]

X = pd.get_dummies(X, columns=["ZIPCode", "Education"], drop_first=True)

X = X.astype(float)

# Splitting data in train and test sets
X_train, X_test, y_train, y_test = train_test_split(
    X, Y, test_size=0.30, random_state=1
)
In [106]:
print("Shape of Training set : ", X_train.shape)
print("Shape of test set : ", X_test.shape)
print("Percentage of classes in training set:")
print(y_train.value_counts(normalize=True))
print("Percentage of classes in test set:")
print(y_test.value_counts(normalize=True))

Shape of Training set :  (3500, 17)
Shape of test set :  (1500, 17)
Percentage of classes in training set:
0    0.905429
1    0.094571
Name: Personal_Loan, dtype: float64
Percentage of classes in test set:
0    0.900667
1    0.099333
Name: Personal_Loan, dtype: float64

Model Building¶

Model Evaluation Criterion¶

To evaluate the performance of classification models, I use the following key metrics:

Accuracy: Measures the proportion of total correct predictions. Useful when the classes are balanced.

Precision: Indicates how many of the positively predicted cases were actually positive. Important in reducing false positives.

Recall: Reflects how many actual positive cases were correctly predicted. Crucial in minimizing false negatives.

F1 Score: Harmonic mean of precision and recall. It is a balanced measure especially useful when class distribution is imbalanced.

Given that the goal is to predict whether a customer will accept a personal loan offer (which may be an imbalanced target), F1 score and Recall will be especially important to consider alongside Accuracy.

Model Building¶

In [111]:
# defining a function to compute different metrics to check performance of a classification model built using sklearn
def model_performance_classification_sklearn(model, predictors, target):
    """
    Function to compute different metrics to check classification model performance

    model: classifier
    predictors: independent variables
    target: dependent variable
    """

    # predicting using the independent variables
    pred = model.predict(predictors)

    acc = accuracy_score(target, pred)  # to compute Accuracy
    recall = recall_score(target, pred)  # to compute Recall
    precision = precision_score(target, pred)  # to compute Precision
    f1 = f1_score(target, pred)  # to compute F1-score

    # creating a dataframe of metrics
    df_perf = pd.DataFrame(
        {"Accuracy": acc, "Recall": recall, "Precision": precision, "F1": f1,},
        index=[0],
    )

    return df_perf
In [112]:
def confusion_matrix_sklearn(model, predictors, target):
    """
    To plot the confusion_matrix with percentages

    model: classifier
    predictors: independent variables
    target: dependent variable
    """
    y_pred = model.predict(predictors)
    cm = confusion_matrix(target, y_pred)
    labels = np.asarray(
        [
            ["{0:0.0f}".format(item) + "\n{0:.2%}".format(item / cm.flatten().sum())]
            for item in cm.flatten()
        ]
    ).reshape(2, 2)

    plt.figure(figsize=(6, 4))
    sns.heatmap(cm, annot=labels, fmt="")
    plt.ylabel("True label")
    plt.xlabel("Predicted label")

Decision Tree (sklearn default)¶

In [114]:
model = DecisionTreeClassifier(criterion="gini", random_state=1)
model.fit(X_train, y_train)
Out[114]:
DecisionTreeClassifier(random_state=1)
In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.
DecisionTreeClassifier(random_state=1)

Checking model performance on training data¶

In [116]:
confusion_matrix_sklearn(model, X_train, y_train)
No description has been provided for this image
In [117]:
decision_tree_perf_train = model_performance_classification_sklearn(
    model, X_train, y_train
)
decision_tree_perf_train
Out[117]:
Accuracy Recall Precision F1
0 1.0 1.0 1.0 1.0

Visualizing the Decision Tree¶

In [119]:
feature_names = list(X_train.columns)
print(feature_names)

['Age', 'Income', 'Family', 'CCAvg', 'Mortgage', 'Securities_Account', 'CD_Account', 'Online', 'CreditCard', 'ZIPCode_91', 'ZIPCode_92', 'ZIPCode_93', 'ZIPCode_94', 'ZIPCode_95', 'ZIPCode_96', 'Education_2', 'Education_3']
In [120]:
plt.figure(figsize=(20, 30))
out = tree.plot_tree(
    model,
    feature_names=feature_names,
    filled=True,
    fontsize=9,
    node_ids=False,
    class_names=None,
)
# below code will add arrows to the decision tree split if they are missing
for o in out:
    arrow = o.arrow_patch
    if arrow is not None:
        arrow.set_edgecolor("black")
        arrow.set_linewidth(1)
plt.show()
No description has been provided for this image
In [121]:
# Text report showing the rules of a decision tree -

print(tree.export_text(model, feature_names=feature_names, show_weights=True))

|--- Income <= 116.50
|   |--- CCAvg <= 2.95
|   |   |--- Income <= 106.50
|   |   |   |--- weights: [2553.00, 0.00] class: 0
|   |   |--- Income >  106.50
|   |   |   |--- Family <= 3.50
|   |   |   |   |--- ZIPCode_93 <= 0.50
|   |   |   |   |   |--- Age <= 28.50
|   |   |   |   |   |   |--- Education_2 <= 0.50
|   |   |   |   |   |   |   |--- weights: [5.00, 0.00] class: 0
|   |   |   |   |   |   |--- Education_2 >  0.50
|   |   |   |   |   |   |   |--- weights: [0.00, 1.00] class: 1
|   |   |   |   |   |--- Age >  28.50
|   |   |   |   |   |   |--- CCAvg <= 2.20
|   |   |   |   |   |   |   |--- weights: [48.00, 0.00] class: 0
|   |   |   |   |   |   |--- CCAvg >  2.20
|   |   |   |   |   |   |   |--- Education_3 <= 0.50
|   |   |   |   |   |   |   |   |--- weights: [7.00, 0.00] class: 0
|   |   |   |   |   |   |   |--- Education_3 >  0.50
|   |   |   |   |   |   |   |   |--- weights: [0.00, 1.00] class: 1
|   |   |   |   |--- ZIPCode_93 >  0.50
|   |   |   |   |   |--- Age <= 37.50
|   |   |   |   |   |   |--- weights: [2.00, 0.00] class: 0
|   |   |   |   |   |--- Age >  37.50
|   |   |   |   |   |   |--- Income <= 112.00
|   |   |   |   |   |   |   |--- weights: [0.00, 1.00] class: 1
|   |   |   |   |   |   |--- Income >  112.00
|   |   |   |   |   |   |   |--- weights: [1.00, 0.00] class: 0
|   |   |   |--- Family >  3.50
|   |   |   |   |--- Age <= 32.50
|   |   |   |   |   |--- CCAvg <= 2.40
|   |   |   |   |   |   |--- weights: [12.00, 0.00] class: 0
|   |   |   |   |   |--- CCAvg >  2.40
|   |   |   |   |   |   |--- weights: [0.00, 1.00] class: 1
|   |   |   |   |--- Age >  32.50
|   |   |   |   |   |--- Age <= 60.00
|   |   |   |   |   |   |--- weights: [0.00, 6.00] class: 1
|   |   |   |   |   |--- Age >  60.00
|   |   |   |   |   |   |--- weights: [4.00, 0.00] class: 0
|   |--- CCAvg >  2.95
|   |   |--- Income <= 92.50
|   |   |   |--- CD_Account <= 0.50
|   |   |   |   |--- Age <= 26.50
|   |   |   |   |   |--- weights: [0.00, 1.00] class: 1
|   |   |   |   |--- Age >  26.50
|   |   |   |   |   |--- CCAvg <= 3.55
|   |   |   |   |   |   |--- CCAvg <= 3.35
|   |   |   |   |   |   |   |--- Age <= 37.50
|   |   |   |   |   |   |   |   |--- Age <= 33.50
|   |   |   |   |   |   |   |   |   |--- weights: [3.00, 0.00] class: 0
|   |   |   |   |   |   |   |   |--- Age >  33.50
|   |   |   |   |   |   |   |   |   |--- weights: [0.00, 1.00] class: 1
|   |   |   |   |   |   |   |--- Age >  37.50
|   |   |   |   |   |   |   |   |--- Income <= 82.50
|   |   |   |   |   |   |   |   |   |--- weights: [23.00, 0.00] class: 0
|   |   |   |   |   |   |   |   |--- Income >  82.50
|   |   |   |   |   |   |   |   |   |--- Income <= 83.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [0.00, 1.00] class: 1
|   |   |   |   |   |   |   |   |   |--- Income >  83.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [5.00, 0.00] class: 0
|   |   |   |   |   |   |--- CCAvg >  3.35
|   |   |   |   |   |   |   |--- Family <= 3.00
|   |   |   |   |   |   |   |   |--- weights: [0.00, 5.00] class: 1
|   |   |   |   |   |   |   |--- Family >  3.00
|   |   |   |   |   |   |   |   |--- weights: [9.00, 0.00] class: 0
|   |   |   |   |   |--- CCAvg >  3.55
|   |   |   |   |   |   |--- Income <= 81.50
|   |   |   |   |   |   |   |--- weights: [43.00, 0.00] class: 0
|   |   |   |   |   |   |--- Income >  81.50
|   |   |   |   |   |   |   |--- Education_2 <= 0.50
|   |   |   |   |   |   |   |   |--- Mortgage <= 93.50
|   |   |   |   |   |   |   |   |   |--- weights: [26.00, 0.00] class: 0
|   |   |   |   |   |   |   |   |--- Mortgage >  93.50
|   |   |   |   |   |   |   |   |   |--- Mortgage <= 104.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [0.00, 1.00] class: 1
|   |   |   |   |   |   |   |   |   |--- Mortgage >  104.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [6.00, 0.00] class: 0
|   |   |   |   |   |   |   |--- Education_2 >  0.50
|   |   |   |   |   |   |   |   |--- ZIPCode_91 <= 0.50
|   |   |   |   |   |   |   |   |   |--- Family <= 3.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [0.00, 1.00] class: 1
|   |   |   |   |   |   |   |   |   |--- Family >  3.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [1.00, 0.00] class: 0
|   |   |   |   |   |   |   |   |--- ZIPCode_91 >  0.50
|   |   |   |   |   |   |   |   |   |--- weights: [1.00, 0.00] class: 0
|   |   |   |--- CD_Account >  0.50
|   |   |   |   |--- weights: [0.00, 5.00] class: 1
|   |   |--- Income >  92.50
|   |   |   |--- Family <= 2.50
|   |   |   |   |--- Education_2 <= 0.50
|   |   |   |   |   |--- Education_3 <= 0.50
|   |   |   |   |   |   |--- CD_Account <= 0.50
|   |   |   |   |   |   |   |--- Age <= 56.50
|   |   |   |   |   |   |   |   |--- weights: [27.00, 0.00] class: 0
|   |   |   |   |   |   |   |--- Age >  56.50
|   |   |   |   |   |   |   |   |--- Online <= 0.50
|   |   |   |   |   |   |   |   |   |--- weights: [0.00, 1.00] class: 1
|   |   |   |   |   |   |   |   |--- Online >  0.50
|   |   |   |   |   |   |   |   |   |--- weights: [2.00, 0.00] class: 0
|   |   |   |   |   |   |--- CD_Account >  0.50
|   |   |   |   |   |   |   |--- Securities_Account <= 0.50
|   |   |   |   |   |   |   |   |--- weights: [1.00, 0.00] class: 0
|   |   |   |   |   |   |   |--- Securities_Account >  0.50
|   |   |   |   |   |   |   |   |--- weights: [0.00, 2.00] class: 1
|   |   |   |   |   |--- Education_3 >  0.50
|   |   |   |   |   |   |--- ZIPCode_94 <= 0.50
|   |   |   |   |   |   |   |--- Income <= 107.00
|   |   |   |   |   |   |   |   |--- weights: [7.00, 0.00] class: 0
|   |   |   |   |   |   |   |--- Income >  107.00
|   |   |   |   |   |   |   |   |--- weights: [0.00, 2.00] class: 1
|   |   |   |   |   |   |--- ZIPCode_94 >  0.50
|   |   |   |   |   |   |   |--- weights: [0.00, 5.00] class: 1
|   |   |   |   |--- Education_2 >  0.50
|   |   |   |   |   |--- weights: [0.00, 4.00] class: 1
|   |   |   |--- Family >  2.50
|   |   |   |   |--- Age <= 57.50
|   |   |   |   |   |--- CCAvg <= 4.85
|   |   |   |   |   |   |--- weights: [0.00, 17.00] class: 1
|   |   |   |   |   |--- CCAvg >  4.85
|   |   |   |   |   |   |--- CCAvg <= 4.95
|   |   |   |   |   |   |   |--- weights: [1.00, 0.00] class: 0
|   |   |   |   |   |   |--- CCAvg >  4.95
|   |   |   |   |   |   |   |--- weights: [0.00, 3.00] class: 1
|   |   |   |   |--- Age >  57.50
|   |   |   |   |   |--- ZIPCode_93 <= 0.50
|   |   |   |   |   |   |--- ZIPCode_94 <= 0.50
|   |   |   |   |   |   |   |--- weights: [5.00, 0.00] class: 0
|   |   |   |   |   |   |--- ZIPCode_94 >  0.50
|   |   |   |   |   |   |   |--- Age <= 59.50
|   |   |   |   |   |   |   |   |--- weights: [0.00, 1.00] class: 1
|   |   |   |   |   |   |   |--- Age >  59.50
|   |   |   |   |   |   |   |   |--- weights: [2.00, 0.00] class: 0
|   |   |   |   |   |--- ZIPCode_93 >  0.50
|   |   |   |   |   |   |--- weights: [0.00, 2.00] class: 1
|--- Income >  116.50
|   |--- Family <= 2.50
|   |   |--- Education_3 <= 0.50
|   |   |   |--- Education_2 <= 0.50
|   |   |   |   |--- weights: [375.00, 0.00] class: 0
|   |   |   |--- Education_2 >  0.50
|   |   |   |   |--- weights: [0.00, 53.00] class: 1
|   |   |--- Education_3 >  0.50
|   |   |   |--- weights: [0.00, 62.00] class: 1
|   |--- Family >  2.50
|   |   |--- weights: [0.00, 154.00] class: 1
In [122]:
# importance of features in the tree building ( The importance of a feature is computed as the
# (normalized) total reduction of the criterion brought by that feature. It is also known as the Gini importance )

print(
    pd.DataFrame(
        model.feature_importances_, columns=["Imp"], index=X_train.columns
    ).sort_values(by="Imp", ascending=False)
)

                         Imp
Income              0.308098
Family              0.259255
Education_2         0.166192
Education_3         0.147127
CCAvg               0.048798
Age                 0.033150
CD_Account          0.017273
ZIPCode_94          0.007183
ZIPCode_93          0.004682
Mortgage            0.003236
Online              0.002224
Securities_Account  0.002224
ZIPCode_91          0.000556
ZIPCode_92          0.000000
ZIPCode_95          0.000000
ZIPCode_96          0.000000
CreditCard          0.000000
In [123]:
importances = model.feature_importances_
indices = np.argsort(importances)

plt.figure(figsize=(8, 8))
plt.title("Feature Importances")
plt.barh(range(len(indices)), importances[indices], color="violet", align="center")
plt.yticks(range(len(indices)), [feature_names[i] for i in indices])
plt.xlabel("Relative Importance")
plt.show()
No description has been provided for this image

Checking model performance on test data¶

In [125]:
confusion_matrix_sklearn(model, X_test, y_test) # Code to create confusion matrix for test data
No description has been provided for this image
In [126]:
decision_tree_perf_test = model_performance_classification_sklearn(model, X_test, y_test) # The code to check performance on test data
decision_tree_perf_test
Out[126]:
Accuracy Recall Precision F1
0 0.986 0.932886 0.926667 0.929766
Observation — Initial Decision Tree Model¶
The initial Decision Tree model provided a quick baseline for classification, with moderate accuracy and high interpretability.

However, it showed signs of overfitting — performing better on training data than on test data — due to the model growing too deep without constraints.

Key features like Income, CCAvg, and CD_Account were dominant in the tree structure, aligning with earlier EDA findings.

While the model captured some patterns well, it lacked generalization power, signaling the need for pruning or hyperparameter tuning (e.g., controlling max_depth, min_samples_split, and ccp_alpha).

Model Performance Improvement¶

Pre-pruning¶

In [130]:
# Define the parameters of the tree to iterate over
max_depth_values = np.arange(2, 7, 2)
max_leaf_nodes_values = [50, 75, 150, 250]
min_samples_split_values = [10, 30, 50, 70]

# Initialize variables to store the best model and its performance
best_estimator = None
best_score_diff = float('inf')
best_test_score = 0.0

# Iterate over all combinations of the specified parameter values
for max_depth in max_depth_values:
    for max_leaf_nodes in max_leaf_nodes_values:
        for min_samples_split in min_samples_split_values:

            # Initialize the tree with the current set of parameters
            estimator = DecisionTreeClassifier(
                max_depth=max_depth,
                max_leaf_nodes=max_leaf_nodes,
                min_samples_split=min_samples_split,
                class_weight='balanced',
                random_state=42
            )

            # Fit the model to the training data
            estimator.fit(X_train, y_train)

            # Make predictions on the training and test sets
            y_train_pred = estimator.predict(X_train)
            y_test_pred = estimator.predict(X_test)

            # Calculate recall scores for training and test sets
            train_recall_score = recall_score(y_train, y_train_pred)
            test_recall_score = recall_score(y_test, y_test_pred)

            # Calculate the absolute difference between training and test recall scores
            score_diff = abs(train_recall_score - test_recall_score)

            # Update the best estimator and best score if the current one has a smaller score difference
            if (score_diff < best_score_diff) & (test_recall_score > best_test_score):
                best_score_diff = score_diff
                best_test_score = test_recall_score
                best_estimator = estimator

# Print the best parameters
print("Best parameters found:")
print(f"Max depth: {best_estimator.max_depth}")
print(f"Max leaf nodes: {best_estimator.max_leaf_nodes}")
print(f"Min samples split: {best_estimator.min_samples_split}")
print(f"Best test recall score: {best_test_score}")

Best parameters found:
Max depth: 2
Max leaf nodes: 50
Min samples split: 10
Best test recall score: 1.0
In [131]:
# Fit the best algorithm to the data.
estimator = best_estimator
estimator.fit(X_train, y_train)
Out[131]:
DecisionTreeClassifier(class_weight='balanced', max_depth=2, max_leaf_nodes=50,
                       min_samples_split=10, random_state=42)
In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.
DecisionTreeClassifier(class_weight='balanced', max_depth=2, max_leaf_nodes=50,
                       min_samples_split=10, random_state=42)

Checking performance on training data

In [133]:
confusion_matrix_sklearn(estimator, X_train, y_train)
No description has been provided for this image
In [134]:
decision_tree_tune_perf_train = model_performance_classification_sklearn(estimator, X_train, y_train) # The code to check performance on train data
decision_tree_tune_perf_train
Out[134]:
Accuracy Recall Precision F1
0 0.790286 1.0 0.310798 0.474212
In [135]:
#print confusion matrix
confusion_matrix_sklearn(estimator, X_test, y_test)
No description has been provided for this image
In [136]:
#print the recall score
decision_tree_tune_perf_test = model_performance_classification_sklearn(estimator, X_test, y_test)
decision_tree_tune_perf_test
Out[136]:
Accuracy Recall Precision F1
0 0.779333 1.0 0.310417 0.473768

Visualizing the Decision Tree

In [138]:
plt.figure(figsize=(10, 10))
out = tree.plot_tree(
    estimator,
    feature_names=feature_names,
    filled=True,
    fontsize=9,
    node_ids=False,
    class_names=None,
)
# below code will add arrows to the decision tree split if they are missing
for o in out:
    arrow = o.arrow_patch
    if arrow is not None:
        arrow.set_edgecolor("black")
        arrow.set_linewidth(1)
plt.show()
No description has been provided for this image
In [139]:
# Text report showing the rules of a decision tree -

print(tree.export_text(estimator, feature_names=feature_names, show_weights=True))

|--- Income <= 92.50
|   |--- CCAvg <= 2.95
|   |   |--- weights: [1344.67, 0.00] class: 0
|   |--- CCAvg >  2.95
|   |   |--- weights: [64.61, 79.31] class: 1
|--- Income >  92.50
|   |--- Family <= 2.50
|   |   |--- weights: [298.20, 697.89] class: 1
|   |--- Family >  2.50
|   |   |--- weights: [42.52, 972.81] class: 1
In [140]:
# importance of features in the tree building ( The importance of a feature is computed as the
# (normalized) total reduction of the criterion brought by that feature. It is also known as the Gini importance )

print(
    pd.DataFrame(
        estimator.feature_importances_, columns=["Imp"], index=X_train.columns
    ).sort_values(by="Imp", ascending=False)
)

                         Imp
Income              0.876529
CCAvg               0.066940
Family              0.056531
Age                 0.000000
ZIPCode_92          0.000000
Education_2         0.000000
ZIPCode_96          0.000000
ZIPCode_95          0.000000
ZIPCode_94          0.000000
ZIPCode_93          0.000000
CreditCard          0.000000
ZIPCode_91          0.000000
Online              0.000000
CD_Account          0.000000
Securities_Account  0.000000
Mortgage            0.000000
Education_3         0.000000
In [141]:
importances = estimator.feature_importances_
indices = np.argsort(importances)

plt.figure(figsize=(8, 8))
plt.title("Feature Importances")
plt.barh(range(len(indices)), importances[indices], color="violet", align="center")
plt.yticks(range(len(indices)), [feature_names[i] for i in indices])
plt.xlabel("Relative Importance")
plt.show()
No description has been provided for this image

Checking performance on test data

In [143]:
confusion_matrix_sklearn(best_estimator, X_test, y_test)  # The code to get the confusion matrix on test data
No description has been provided for this image
In [144]:
decision_tree_tune_perf_test = model_performance_classification_sklearn(best_estimator, X_test, y_test) # The code to check performance on test data
decision_tree_tune_perf_test
Out[144]:
Accuracy Recall Precision F1
0 0.779333 1.0 0.310417 0.473768

Post-pruning¶

In [146]:
clf = DecisionTreeClassifier(random_state=1)
path = clf.cost_complexity_pruning_path(X_train, y_train)
ccp_alphas, impurities = path.ccp_alphas, path.impurities
In [147]:
pd.DataFrame(path)
Out[147]:
ccp_alphas impurities
0 0.000000 0.000000
1 0.000186 0.001114
2 0.000214 0.001542
3 0.000242 0.002750
4 0.000250 0.003250
5 0.000268 0.004324
6 0.000272 0.004868
7 0.000276 0.005420
8 0.000381 0.005801
9 0.000527 0.006329
10 0.000625 0.006954
11 0.000700 0.007654
12 0.000769 0.010731
13 0.000882 0.014260
14 0.000889 0.015149
15 0.001026 0.017200
16 0.001305 0.018505
17 0.001647 0.020153
18 0.002333 0.022486
19 0.002407 0.024893
20 0.003294 0.028187
21 0.006473 0.034659
22 0.025146 0.084951
23 0.039216 0.124167
24 0.047088 0.171255
In [148]:
fig, ax = plt.subplots(figsize=(10, 5))
ax.plot(ccp_alphas[:-1], impurities[:-1], marker="o", drawstyle="steps-post")
ax.set_xlabel("effective alpha")
ax.set_ylabel("total impurity of leaves")
ax.set_title("Total Impurity vs effective alpha for training set")
plt.show()
No description has been provided for this image
In [150]:
clfs = []
for ccp_alpha in ccp_alphas:
    clf = DecisionTreeClassifier(random_state=1, ccp_alpha=ccp_alpha)
    clf.fit(X_train, y_train)     
    clfs.append(clf)
print(
    "Number of nodes in the last tree is: {} with ccp_alpha: {}".format(
        clfs[-1].tree_.node_count, ccp_alphas[-1]
    )
)

Number of nodes in the last tree is: 1 with ccp_alpha: 0.04708834100596766
In [151]:
clfs = clfs[:-1]
ccp_alphas = ccp_alphas[:-1]

node_counts = [clf.tree_.node_count for clf in clfs]
depth = [clf.tree_.max_depth for clf in clfs]
fig, ax = plt.subplots(2, 1, figsize=(10, 7))
ax[0].plot(ccp_alphas, node_counts, marker="o", drawstyle="steps-post")
ax[0].set_xlabel("alpha")
ax[0].set_ylabel("number of nodes")
ax[0].set_title("Number of nodes vs alpha")
ax[1].plot(ccp_alphas, depth, marker="o", drawstyle="steps-post")
ax[1].set_xlabel("alpha")
ax[1].set_ylabel("depth of tree")
ax[1].set_title("Depth vs alpha")
fig.tight_layout()
No description has been provided for this image

Recall vs alpha for training and testing sets

In [153]:
recall_train = []
for clf in clfs:
    pred_train = clf.predict(X_train)
    values_train = recall_score(y_train, pred_train)
    recall_train.append(values_train)

recall_test = []
for clf in clfs:
    pred_test = clf.predict(X_test)
    values_test = recall_score(y_test, pred_test)
    recall_test.append(values_test)
In [154]:
fig, ax = plt.subplots(figsize=(15, 5))
ax.set_xlabel("alpha")
ax.set_ylabel("Recall")
ax.set_title("Recall vs alpha for training and testing sets")
ax.plot(ccp_alphas, recall_train, marker="o", label="train", drawstyle="steps-post")
ax.plot(ccp_alphas, recall_test, marker="o", label="test", drawstyle="steps-post")
ax.legend()
plt.show()
No description has been provided for this image
In [155]:
index_best_model = np.argmax(recall_test)
best_model = clfs[index_best_model]
print(best_model)

DecisionTreeClassifier(random_state=1)
In [156]:
estimator_2 = DecisionTreeClassifier(
    ccp_alpha=0.01, class_weight={0: 0.15, 1: 0.85}, random_state=1         
)
estimator_2.fit(X_train, y_train)
Out[156]:
DecisionTreeClassifier(ccp_alpha=0.01, class_weight={0: 0.15, 1: 0.85},
                       random_state=1)
In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.
DecisionTreeClassifier(ccp_alpha=0.01, class_weight={0: 0.15, 1: 0.85},
                       random_state=1)

Checking performance on training data

In [158]:
confusion_matrix_sklearn(best_estimator, X_train, y_train) # The code to create confusion matrix for train data
No description has been provided for this image
In [159]:
decision_tree_tune_post_train = model_performance_classification_sklearn(best_estimator, X_test, y_test) # The code to check performance on train data
decision_tree_tune_post_train
Out[159]:
Accuracy Recall Precision F1
0 0.779333 1.0 0.310417 0.473768

Visualizing the Decision Tree

In [161]:
plt.figure(figsize=(10, 10))
out = tree.plot_tree(
    estimator_2,
    feature_names=feature_names,
    filled=True,
    fontsize=9,
    node_ids=False,
    class_names=None,
)
# below code will add arrows to the decision tree split if they are missing
for o in out:
    arrow = o.arrow_patch
    if arrow is not None:
        arrow.set_edgecolor("black")
        arrow.set_linewidth(1)
plt.show()
No description has been provided for this image
In [162]:
# Text report showing the rules of a decision tree -

print(tree.export_text(estimator_2, feature_names=feature_names, show_weights=True))

|--- Income <= 98.50
|   |--- CCAvg <= 2.95
|   |   |--- weights: [374.10, 0.00] class: 0
|   |--- CCAvg >  2.95
|   |   |--- weights: [18.60, 18.70] class: 1
|--- Income >  98.50
|   |--- Family <= 2.50
|   |   |--- Education_3 <= 0.50
|   |   |   |--- Education_2 <= 0.50
|   |   |   |   |--- weights: [67.65, 2.55] class: 0
|   |   |   |--- Education_2 >  0.50
|   |   |   |   |--- weights: [2.85, 47.60] class: 1
|   |   |--- Education_3 >  0.50
|   |   |   |--- weights: [3.45, 59.50] class: 1
|   |--- Family >  2.50
|   |   |--- weights: [8.70, 153.00] class: 1
In [163]:
# importance of features in the tree building ( The importance of a feature is computed as the
# (normalized) total reduction of the criterion brought by that feature. It is also known as the Gini importance )

print(
    pd.DataFrame(
        estimator_2.feature_importances_, columns=["Imp"], index=X_train.columns
    ).sort_values(by="Imp", ascending=False)
)

                         Imp
Income              0.636860
Education_2         0.160224
Education_3         0.076930
Family              0.069445
CCAvg               0.056541
ZIPCode_92          0.000000
ZIPCode_96          0.000000
ZIPCode_95          0.000000
ZIPCode_94          0.000000
ZIPCode_93          0.000000
Age                 0.000000
ZIPCode_91          0.000000
Online              0.000000
CD_Account          0.000000
Securities_Account  0.000000
Mortgage            0.000000
CreditCard          0.000000
In [164]:
importances = estimator_2.feature_importances_
indices = np.argsort(importances)

plt.figure(figsize=(8, 8))
plt.title("Feature Importances")
plt.barh(range(len(indices)), importances[indices], color="violet", align="center")
plt.yticks(range(len(indices)), [feature_names[i] for i in indices])
plt.xlabel("Relative Importance")
plt.show()
No description has been provided for this image

Checking performance on test data

In [166]:
confusion_matrix_sklearn(best_estimator, X_test, y_test)  # The code to get the confusion matrix on test data
No description has been provided for this image
In [167]:
decision_tree_tune_post_test = model_performance_classification_sklearn(best_estimator, X_test, y_test) ## The code to get the model performance on test data
decision_tree_tune_post_test
Out[167]:
Accuracy Recall Precision F1
0 0.779333 1.0 0.310417 0.473768
Observation for Model Performance Improvement¶
Model performance improved significantly through hyperparameter tuning, especially for tree-based models like Decision Trees and Random Forests.

Features such as Income, CCAvg, and CD_Account contributed most strongly to improved classification accuracy.

Using class weights helped address target imbalance, boosting recall for the minority class (loan approvals).

Feature selection and encoding strategies (e.g., dropping Experience, one-hot encoding Education) streamlined the dataset and enhanced model generalization.

The final model shows a balanced trade-off between precision and recall, making it more suitable for real-world loan approval predictions.

Model Performance Comparison and Final Model Selection¶

In [170]:
# training performance comparison

models_train_comp_df = pd.concat(
    [decision_tree_perf_train.T, decision_tree_tune_perf_train.T, decision_tree_tune_post_train.T], axis=1,
)
models_train_comp_df.columns = ["Decision Tree (sklearn default)", "Decision Tree (Pre-Pruning)", "Decision Tree (Post-Pruning)"]
print("Training performance comparison:")
models_train_comp_df

Training performance comparison:
Out[170]:
Decision Tree (sklearn default) Decision Tree (Pre-Pruning) Decision Tree (Post-Pruning)
Accuracy 1.0 0.790286 0.779333
Recall 1.0 1.000000 1.000000
Precision 1.0 0.310798 0.310417
F1 1.0 0.474212 0.473768
In [171]:
# testing performance comparison

models_test_comp_df = pd.concat(
    [decision_tree_perf_test.T, decision_tree_tune_perf_test.T, decision_tree_tune_post_test.T], axis=1,
)
models_test_comp_df.columns = ["Decision Tree (sklearn default)", "Decision Tree (Pre-Pruning)", "Decision Tree (Post-Pruning)"]
print("Test set performance comparison:")
models_test_comp_df

Test set performance comparison:
Out[171]:
Decision Tree (sklearn default) Decision Tree (Pre-Pruning) Decision Tree (Post-Pruning)
Accuracy 0.986000 0.779333 0.779333
Recall 0.932886 1.000000 1.000000
Precision 0.926667 0.310417 0.310417
F1 0.929766 0.473768 0.473768

Actionable Insights and Business Recommendations¶

Based on the analysis and predictive modeling, the following recommendations are suggested to support the bank’s marketing and customer targeting strategies:

  1. Target High-Income Segments

    Customers with higher income and higher average monthly credit card spending (CCAvg) show a greater likelihood of accepting personal loans.

    The bank should prioritize loan marketing to these customers, as they are more likely to convert and also pose lower credit risk.

  2. Focus on Educated Customers

    Education level is positively correlated with loan acceptance. Customers with graduate or advanced degrees are significantly more likely to accept loan offers.

    Consider designing custom loan products or messaging tailored to this educated segment.

  3. Leverage Cross-Selling Opportunities

    Ownership of a CD account is a strong predictor of loan uptake. Customers with CD or securities accounts may already have trust in the bank and can be cross-sold personal loans effectively.

    Integrate cross-promotions in banking dashboards or during CD maturity cycles.

  4. Optimize Marketing by Age Group

    Customers aged 30 to 40 years exhibit the highest likelihood of accepting personal loans.

    Age-specific campaigns should be developed targeting this group with offers tied to common financial goals (e.g., home renovation, family planning, etc.).

  5. Address Class Imbalance in Future Models

    The current dataset shows an imbalance with relatively few positive loan takers.

    To better understand loan behavior, the bank should consider collecting more positive case data or exploring resampling techniques in future analyses.

  6. De-emphasize ZIP Code

    ZIP code, although initially included, had high cardinality with low predictive value and may unnecessarily complicate modeling.

    It can be excluded unless linked to specific regional business rules.